{"id":"W2394928340","doi":"","title":"Linear Off-Policy Actor-Critic.","year":2012,"lang":"en","type":"article","venue":"","topic":"Complex Systems and Decision Making","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001547238,0.001392062,0.001080173,0.0004312303,0.0003666289,0.001109342,0.00192994,0.001480283,0.006332671],"category_scores_gemma":[0.004555495,0.0005509402,0.0005303457,0.0004327297,0.001210993,0.0009247022,0.001394126,0.002151609,0.0016905],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001327469,"about_ca_system_score_gemma":0.00179421,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004894315,"about_ca_topic_score_gemma":0.004619707,"domain_scores_codex":[0.9992818,0.0002285372,0.00003088417,0.0001542004,0.0002144891,0.00009002309],"domain_scores_gemma":[0.9984437,0.0009760176,0.0001273094,0.0001443958,0.0002190696,0.00008948675],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009511619,0.00006926538,0.0003668589,0.0001144138,0.00004103408,0.00008538886,0.00005189994,0.8971869,0.0007670877,0.03511257,0.003387257,0.06272225],"study_design_scores_gemma":[0.00000854312,0.00001598531,0.00001972803,0.000007009915,0.000004069816,0.00001281632,0.000003157204,0.9924245,0.0002305232,0.006171512,0.001099094,0.000003059264],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003378606,0.0003672804,0.9852054,0.0001934941,0.0001179093,0.00009904931,0.00004241843,0.0009308633,0.009665086],"genre_scores_gemma":[0.6833634,0.0005325128,0.2932845,0.0005802196,0.0001144503,0.0004751658,0.0002769356,0.0003067954,0.02106597],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006332671,"threshold_uncertainty_score":0.02118486,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2907023162025797,"score_gpt":0.4872813471678861,"score_spread":0.1965790309653064,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}